Challenge 9

Loading in libraries/dataset

Code

library(tidyverse)
library(here)
library(broom)
library(knitr)
library(kableExtra)
library(DT)

Code

babyNames <- read_csv(here::here("Week9", "lab9", "StateNames_A.csv")) |> 
  rename(Sex = "Gender")

Interactive dataset for babyNames

Code

datatable(babyNames)

Summarizing & Visualizing the Number of Allisons

Code

babyNames |> 
  mutate(Count = replace_na(Count, 0)) |> 
  group_by(Sex, State) |> 
  filter(Name == "Allison", Sex == "F") |> 
  summarize(total = sum(Count)) |> 
  kable(caption = "<center><strong>Frequencies of babies named 
        Allison by state</strong></center>") |> 
  kable_styling(bootstrap_options = "striped", html_font = "Cambria") 

Frequencies of babies named Allison by state

Sex	State	total
F	AK	232
F	AL	1535
F	AR	1198
F	AZ	1880
F	CA	12413
F	CO	1594
F	CT	1099
F	DC	321
F	DE	294
F	FL	4455
F	GA	3257
F	HI	183
F	IA	1477
F	ID	451
F	IL	5110
F	IN	3067
F	KS	1283
F	KY	1905
F	LA	1209
F	MA	2218
F	MD	2229
F	ME	340
F	MI	4014
F	MN	2374
F	MO	2882
F	MS	817
F	MT	226
F	NC	3435
F	ND	285
F	NE	807
F	NH	412
F	NJ	3052
F	NM	399
F	NV	729
F	NY	5747
F	OH	5487
F	OK	1421
F	OR	1186
F	PA	4307
F	RI	306
F	SC	1228
F	SD	376
F	TN	2488
F	TX	10192
F	UT	1125
F	VA	3220
F	VT	135
F	WA	1956
F	WI	2367
F	WV	813
F	WY	142

Alan dataset

Code

A_names <- babyNames |> 
  filter(Name %in% c("Alan", "Allen", "Allan"), Sex == "M")

Interactive dataset for A_names

Code

datatable(A_names)

Total Counts

Code

A_names |> 
  filter(State %in% c("CA", "PA"), Year == "2000") |> 
  pivot_wider(names_from = Name, values_from = Count) |> 
  mutate(across(Alan:Allan, .fns = replace_na, 0)) |> 
  rowwise() |> 
  mutate(total = sum(Alan, Allen, Allan)) |> 
  kable(caption = "<center><strong>Total counts of Different Alan 
        spellings in CA and PA in 2000</strong></center>") |> 
  kable_styling(bootstrap_options = "striped", html_font = "Cambria") 

Total counts of Different Alan spellings in CA and PA in 2000

Year	Sex	State	Alan	Allen	Allan	total
2000	M	CA	579	176	131	886
2000	M	PA	51	56	12	119

Percentages

Code

A_names |> 
  filter(State %in% c("CA", "PA"), Year == "2000") |> 
  pivot_wider(names_from = Name, values_from = Count) |> 
  mutate(across(Alan:Allan, .fns = replace_na, 0)) |> 
  rowwise() |> 
  mutate(total = sum(Alan, Allen, Allan), Alan = Alan/total * 100, 
         Allen = Allen/total * 100, Allan = Allan/total * 100, 
         totalPct = sum(Alan, Allen, Allan)) |> 
  kable(caption = "<count><strong>Percentages of different Alan 
        spellings in CA and PA in 2000 rounded 
        to 2 decimal places</strong></center>", 
        digits = 2) |> 
  kable_styling(bootstrap_options = "striped", html_font = "Cambria") 

Percentages of different Alan spellings in CA and PA in 2000 rounded to 2 decimal places

Year	Sex	State	Alan	Allen	Allan	total	totalPct
2000	M	CA	65.35	19.86	14.79	886	100
2000	M	PA	42.86	47.06	10.08	119	100